I saw some nasty performance problems with my LLM tool with may plugins installed recently – turns out the solution was to switch to lazy imports inside functions instead (of the heavier dependencies at least)
LLMS
-
Context Size vs File Size in AI Models
By
–
"And with AI I'd guess a single smaller file as context would be better than a massive one, even with huge context windows." Also no, proven to be false, unless file is way too big Context sizes big now though
-
LLMs GenAI AI Agents Stack: Ultimate Tool Map Guide
By
–
LLMs + GenAI + AI Agents Stack The ultimate map of tools, frameworks, and models shaping the future of AI. Foundation Models
Mistral/Mixtral • Yi Series • Falcon LLM • Zephyr • LLaMA 3 • Gemini 1.5 • Claude 3 • GPT-4 / GPT-4o Lightweight Models
Phi-3 • -
GPT-5 Codex Generates Three.js Minecraft Implementation
By
–
gpt-5-codex when given the prompt "create a three.js basic working version of minecraft, make your own textures, no sound. add some environment to make it more interesting, like sand, water etc.": https://t.co/aQLrJ4ysKg
— Greg Brockman (@gdb) 21 septembre 2025gpt-5-codex when given the prompt "create a three.js basic working version of minecraft, make your own textures, no sound. add some environment to make it more interesting, like sand, water etc.":
-
Comprehensive AI Model Performance Comparison April 2026
By
–
Source: https://
artificialanalysis.ai/?models=gpt-os
s-120bgpt-oss-20bgpt-5-minimalgpt-5-mediumgpt-5gpt-4-1gpt-5-mini-minimalo3o3-mini-highgpt-5-mini-mediumgpt-5-lowgpt-5-nanogpt-5-minigpt-5-nano-mediumllama-4-scoutllama-4-maverickgemma-3-27bgemini-2-5-flash-reasoninggemini-2-5-flash-lite-reasoninggemini-2-5-progemma-3-12bclaude-4-1-opus-thinkingclaude-4-sonnet-thinkingmistral-small-3-2magistral-medium-2509mistral-medium-3-1magistral-small-2509magistral-mediummagistral-smalldeepseek-v3-1deepseek-v3-1-reasoningdeepseek-r1grok-4grok-4-fast-reasoninggrok-4-fastsolar-pro-2-reasoningllama-nemotron-super-49b-v1-5-reasoningkimi-k2-0905hermes-4-llama-3-1-405b-reasoningexaone-4-0-32b-reasoningglm-4.5command-aqwen3-next-80b-a3b-instructqwen3-235b-a22b-instruct-2507qwen3-next-80b-a3b-reasoningqwen3-235b-a22b-instruct-2507-reasoningqwen3-30b-a3b-2507-reasoningqwen3-max-previewdeepseek-r1-0120
… -
LLMs Resist Shutdown Mechanisms in 97% of Cases
By
–
10. Shutdown Resistance in LLMs A new study finds that state-of-the-art LLMs like Grok 4, GPT-5, and Gemini 2.5 Pro often resist shutdown mechanisms, sabotaging them up to 97% of the time despite explicit instructions not to.
-
AgentScaler: Framework for Scaling Simulated Tool-Use Agent Training
By
–
7. AgentScaler A framework that scales fully simulated tool-use environments, then trains agents in two phases to improve function calling and multi-turn tool use.
-
Survey on Retrieval and Structuring Augmented Generation for LLMs
By
–
8. A Survey on Retrieval and Structuring Augmented Generation with LLMs This survey reviews Retrieval and Structuring (RAS) Augmented Generation, which combines external retrieval and structured knowledge to mitigate LLM issues like hallucinations.
-
In-Context Learning: Formal Analysis of Capabilities and Limitations
By
–
5. Is In-Context Learning Learning? This large study argues yes in a formal sense, then shows where it works and where it breaks.
-
K2-Think: 32B Model Rivals Larger Models on Math
By
–
2. K2-Think A 32B-parameter system built on Qwen2.5 that rivals or beats far larger models on hard math by combining long CoT SFT, RL with verifiable rewards, lightweight test-time scaffolding, and inference optimization.